ClawHub
Back to skill

Security audit

Deep Cognition

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese article-writing style guide with no code execution, data access, persistence, or hidden behavior.

Install this if you want the agent to help write Chinese articles in a strong opinion-and-paradigm style. For multilingual or neutral-tone work, explicitly tell the agent what language and tone to use when invoking the skill.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill is written entirely in Chinese and strongly anchors outputs to that language and style, without indicating that the language should follow user preference. In a multilingual agent system, this can override user intent, reduce accessibility, and cause the agent to respond in an unexpected language, which is a form of prompt-quality and control failure even though it is not overtly malicious.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.